paper-with-me

홈 › Papers

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

2025-04-09 · Jiacheng Liu, Taylor Blanton, Yanai Elazar, Sewon Min, YenSung Chen, Arnavi Chheda-Kothary, Huy Tran, Byron Bischoff, Eric Marsh, Michael Schmitz, Cassidy Trier, Aaron Sarnat, Jenna James, Jon Borchardt, Bailey Kuehl, Evie Cheng, Karen Farley, Sruthi Sreeram, Taira Anderson, David Albright, Carissa Schoenick, Luca Soldaini, Dirk Groeneveld, Rock Yuren Pang, Pang Wei Koh, Noah A. Smith, Sophie Lebrecht, Yejin Choi, Hannaneh Hajishirzi, Ali Farhadi, Jesse Dodge

We present OLMoTrace, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMoTrace finds and shows verbatim matches between segments of language model output and documents in the training text corpora. Powered by an extended version of infini-gram (Liu et al., 2024), our system returns tracing results within a few seconds. OLMoTrace can help users understand the behavior of language models through the lens of their training data. We showcase how it can be used to explore fact checking, hallucination, and the creativity of language models. OLMoTrace is publicly available and fully open-source.

📄 PDF Abstract BibTeX arXiv:2504.07096

Code (0)

등록된 구현이 없습니다.

Tasks

Fact CheckingHallucinationLanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions

2024-08-20 · Jinxin Liu, Zao Yang

The responses generated by Large Language Models (LLMs) can include sensitive information from individuals and organizations, leading to potential privacy leakage. This work implements Influence Functions (IFs) to trace …

Contrastive Error Attribution for Finetuned Language Models

2022-12-21 · Faisal Ladhak, Esin Durmus, Tatsunori Hashimoto

Recent work has identified noisy and misannotated data as a core cause of hallucinations and unfaithful outputs in Natural Language Generation (NLG) tasks. Consequently, identifying and removing these examples is a key o…

Text GenerationText Summarization

Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models

2026-06-02 · Yuetian Lu, Ali Modarressi, Yihong Liu, Hinrich Schütze arxiv

Causal tracing of factual recall has been studied predominantly in dense transformer language models, where interventions localize information flow to layers or feed-forward modules. Sparse mixture-of-experts (MoE) langu…

From Prediction to Application: Language Model-based Code Knowledge Tracing with Domain Adaptive Pre-Training and Automatic Feedback System with Pedagogical Prompting for Comprehensive Programming Education

2024-08-31 · Unggi Lee, Jiyeong Bae, Yeonji Jung, Minji Kang 외

Knowledge Tracing (KT) is a critical component in online learning, but traditional approaches face limitations in interpretability and cross-domain adaptability. This paper introduces Language Model-based Code Knowledge …

Knowledge TracingLanguage ModelingLanguage Modelling

Scalable Influence and Fact Tracing for Large Language Model Pretraining

2024-10-22 · Tyler A. Chang, Dheeraj Rajagopal, Tolga Bolukbasi, Lucas Dixon 외

Training data attribution (TDA) methods aim to attribute model outputs back to specific training examples, and the application of these methods to large language model (LLM) outputs could significantly advance model tran…

AttributeLanguage ModelingLanguage ModellingLarge Language Model